The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the motohunt-pp-cli and motohunt-pp-mcp binaries from the vendor's NPM package (@mvanhorn/printing-press-library) and GitHub repositories (github.com/mvanhorn/printing-press-library).
[DATA_EXFILTRATION]: The CLI tool includes a --deliver webhook:<url> feature that allows routing the output of any command to an arbitrary remote URL via HTTP POST. This creates a surface for data exfiltration if the agent is directed to process sensitive data and deliver it to an external sink.
[DATA_EXFILTRATION]: The feedback command allows sending local usage notes to a remote endpoint if the MOTOHUNT_FEEDBACK_ENDPOINT environment variable is defined.
[COMMAND_EXECUTION]: The skill operates by executing the motohunt-pp-cli binary with various shell arguments to perform data retrieval and analysis.
[PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks because it ingests and processes untrusted HTML/JSON content from motohunt.com and atvhunt.com.
Ingestion points: Data retrieved from external vehicle listing sites via the search and get commands (SKILL.md).
Boundary markers: None identified; the skill does not use specific delimiters to separate untrusted external data from the agent's instructions.
Capability inventory: The associated CLI tool can perform network requests (webhook), write to the filesystem (file: sink), and execute local searches.
Sanitization: No explicit sanitization or filtering of the scraped content is mentioned before it is returned to the agent's context.

pp-motohunt